Aug 2026· Veredas do Direito· Vol 23, pp. e238046· 0 citations· 25 references
TL;DR
It is demonstrated that the hybrid AI-human model achieved high diagnostic performance for ruling out proximal DVT, with a sensitivity of 90-100% and a negative predictive value (NVP) of 87.5-100%.
Abstract
Deep vein thrombosis (DVT) is a significant global health burden. Point-of-care ultrasound (POCUS) enhances diagnostic access but is dependent on the operator. Artificial intelligence (AI) has been proposed to guide novices and standardize image acquisition, often within a hybrid model incorporating remote clinician review. This systematic review aimed to synthesize the diagnostic accuracy, clinical feasibility, and health economic impact of AI-guided POCUS for DVT diagnosis within AI-human hybrid models. This systematic review was conducted in accordance with PRISMA guidelines, searching databases (PubMed/Medline, Scopus, Web of Science, IEEE, and Google Scholar) for studies published between 2021 and 2025. Four studies met the eligibility criteria, assessing AI-guided POCUS systems for DVT diagnosis. These studies demonstrated that the hybrid AI-human model achieved high diagnostic performance for ruling out proximal DVT, with a sensitivity of 90-100% and a negative predictive value (NVP) of 87.5-100%. Reviewer expertise significantly impacted accuracy; emergency medicine POCUS-trained physicians outperformed general radiologists. The model was feasible for non-expert operators (e.g., nurses) with minimal training and showed potential to reduce unnecessary duplex ultrasound referrals by 29–58%, with associated workflow efficiency. AI-guided POCUS combined with mandatory clinician review forms an effective hybrid model that enhances access, standardizes quality, and safely rules out DVT. Successful real-world implementation requires targeted reviewer training, workflow integration, and further health economic and independent pragmatic evaluation.
The development of AI systems to support LUS interpretation shows high potential; however, current studies exhibit significant heterogeneity in their objectives, methodologies, and evaluation metrics.
Julia López-Canay, Alberto Fernández-Villar, Cristina Ramos-Hernández et al.· Frontiers in Radiology· 1 citation
Artificial intelligence (AI) has emerged as a promising tool for improving the diagnostic accuracy of breast ultrasound and facilitating early breast cancer detection. This systematic review evaluated the current evidence on AI-based diagnostic models for breast ultrasound imaging. A systematic literature search was performed in PubMed, Scilit, and PMC following the PRISMA 2020 guidelines. A total of 1,296 records were identified, and after duplicate removal and eligibility screening, 18 studies published between 2021 and 2026 were included. Methodological quality was assessed using the QUADAS-3 tool. Owing to heterogeneity in AI models, study designs, and reported outcomes, a qualitative synthesis was conducted without quantitative meta-analysis. AI-assisted breast ultrasound demonstrated generally favourable diagnostic performance, although the reported parameters varied across studies. Sensitivity ranged from 71.4% to 100.0%, specificity from 71.6% to 96.2%, and AUC from 0.778 to 1.00. One EfficientNet-B7 model integrated with explainable AI achieved an AUC of 1.00, sensitivity of 99.5%, an F1-score of 98.9%, and accuracy of 99.14%, representing one of the highest-performing models identified. Other high-performing approaches included hybrid deep learning, Vision Transformers, interpretable ensemble transformers, convolutional neural networks, and machine learning models, which improved lesion classification, reduced false-positive findings, enhanced interpretability, and supported standardized reporting. However, most studies were retrospective, single-center investigations with limited external validation. AI-assisted breast ultrasound is a promising adjunctive tool for early breast cancer detection. Although current evidence supports its clinical potential, further prospective multicenter studies with standardized methodologies and external validation are needed before routine clinical implementation.
W. A. Utami, Siti Wahyuni, Miska Zamharira et al.· Narra Review· 0 citations
Background: Large vessel occlusion (LVO) is a major cause of morbidity and mortality in acute ischemic stroke (AIS) and a common indication for mechanical thrombectomy. Rapid detection is critical because the benefit of treatment is highly time-dependent. Artificial intelligence (AI)-based imaging systems have emerged as decision-support tools for automated LVO identification, image prioritisation, and rapid stroke-team notification.
Objective: To critically review current evidence on AI-assisted LVO detection, including diagnostic accuracy, clinical and workflow implications, commercially available platforms, barriers to implementation, and future perspectives.
Methods: This narrative review covers literature published from January 2015 to June 2026 on AI-based LVO identification using computed tomography angiography (CTA) and multimodal stroke imaging. Evidence relating to diagnostic performance, external validation, workflow impact, commercial platforms, implementation, and emerging technologies was reviewed.
Results: AI systems demonstrate high diagnostic accuracy for proximal anterior circulation LVO, with reported sensitivities of 85-97% and specificities above 90%. Clinical implementation has improved image triage, specialist notification, thrombectomy activation, and interhospital coordination. However, performance is less consistent for distal and posterior circulation occlusions, while heterogeneity in study design, imaging methods, and outcome measures limits comparisons between platforms. Additional challenges include false-positive alerts, missed occlusions, limited generalisability, algorithmic bias, explainability, regulatory oversight, interoperability, and cost.
Conclusion: AI-assisted LVO detection has the potential to improve the speed and coordination of acute stroke care, particularly for proximal anterior circulation occlusions, but should augment rather than replace clinician interpretation. Its long-term clinical value requires prospective multicentre validation, standardised comparative studies, transparent reporting, and evaluation of patient-centred outcomes.
Keywords: Artificial Intelligence; Large Vessel Occlusion; Acute Ischemic Stroke; Mechanical Thrombectomy; Computed Tomography Angiography; Stroke Imaging; Clinical Decision Support; Machine Learning.
Ishaan Bakshi· The Operating Room Global Jo...· 0 citations
The role of AI-enhanced cardiovascular ultrasound in the transition from descriptive imaging toward predictive and personalized medicine is examined, with AI-enhanced cardiovascular ultrasound poised to become a central tool of precision cardiology.
Ancuța Elena Țupu, Simona Steliana Tudor, C. Dumitru et al.· Journal of Clinical Medicine· 0 citations
Pulmonary embolism (PE) is a life-threatening condition commonly diagnosed with computed tomography pulmonary angiography (CTPA). Although artificial intelligence (AI) has been applied for PE detection, its performance relative to physician-only and AI-assisted interpretation remains incompletely characterized. The study aimed to evaluate the diagnostic performance and reading time across 3 CTPA interpretation strategies: AI alone, physician-only reading, and AI-assisted physician reading. We retrospectively analyzed CTPA images from 50 patients diagnosed with PE at a single center and randomly divided them into 2 groups: one group (n = 25) was reviewed by radiologists from different levels, and the other group (n = 25) was reviewed by radiologists with AI assistance. Then, AI independently reviewed all images. The reference standard was established by consensus among 3 senior radiologists. Diagnostic performance and reading time were compared across the 3 reading paradigms. AI alone achieved an overall sensitivity of 91.24% and precision of 96.12%; sensitivity declined from 100% in grade 1 to 2 vessels to 86.32% in grade ≥6 vessels. Compared with physician-only reading, AI-assisted reading increased sensitivity and precision for junior radiologists (64.28%–75.51% and 81.82%–89.16%, respectively) and intermediate radiologists (80.67%–92.34% and 88.47%–97.31%, respectively). AI assistance also reduced mean reading time at both experience levels (both P < .05). In this small, single-center retrospective exploratory study, AI-assisted CTPA interpretation was associated with higher lesion-level sensitivity and precision and shorter reading times than physician-only interpretation. Larger prospective multicenter studies are required to validate these findings and assess their generalizability.
Hui-Yang Zhang, Min-Jie Dong, Hong-Bo Li et al.· Medicine· 0 citations
INTRODUCTION
This systematic review and meta-analysis evaluated artificial intelligence (AI) and radiomics applied to renal ultrasound for the diagnosis, staging, and prognosis of degenerative kidney disorders.
METHODS
PubMed/MEDLINE, Embase, Scopus, Web of Science, the Cochrane Library, and gray-literature sources were searched without date or language restrictions. Eligible studies applied AI or radiomics to renal ultrasound and reported diagnostic, staging, or prognostic outcomes. Risk of bias and methodological quality were assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST), Checklist for Artificial Intelligence in Medical Imaging (CLAIM 2024), and Radiomics Quality Score 2.0 (RQS 2.0). Random-effects models were used for diagnostic accuracy synthesis.
RESULTS
Thirty-one studies were included. Machine-learning models achieved pooled sensitivity of 0.86 (95% confidence interval 0.82-0.90) and specificity of 0.83 (0.79-0.87); deep-learning models achieved sensitivity of 0.89 (0.84-0.93) and specificity of 0.85 (0.81-0.91). Heterogeneity was substantial and external validation was uncommon.
CONCLUSIONS
AI-augmented renal ultrasound shows promising diagnostic performance, but heterogeneous populations, limited calibration, and predominantly internal validation constrain clinical generalizability. Prospective multicenter external validation is required.
M. Elhaie, Abolfazl Koozari, Amirsaman Soleimani Nasab et al.· Future Science OA· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
